6 papers · 1 filter
Sequential Data Poisoning in LLM Post-Training
Jack Sanderson, Yihan Wang, Xiaoqian Lu +2
LLM post-training proceeds through multiple stages, e.g., supervised fine-tuning (SFT) followed by reinforcement learning from human feedback (RLHF) or direct preference optimizati…
Are Targeted Data Poisoning Attacks as Effective as We Think?
William Xu, Chenyu Zhang, Yihan Wang +5
Targeted data poisoning attacks manipulate model predictions on specific test samples by injecting malicious data into training. Yet existing evaluations report average attack succ…
Machine Unlearning Fails to Remove Data Poisoning Attacks
Martin Pawelczyk, Jimmy Z. Di, Yiwei Lu +3
We revisit the efficacy of several practical methods for approximate machine unlearning developed for large-scale deep learning. In addition to complying with data deletion request…
MUC: Machine Unlearning for Contrastive Learning with Black-box Evaluation
Yihan Wang, Yiwei Lu, Guojun Zhang +4
Machine unlearning offers effective solutions for revoking the influence of specific training data on pre-trained model parameters. While existing approaches address unlearning for…
BridgePure: Limited Protection Leakage Can Break Black-Box Data Protection
Yihan Wang, Yiwei Lu, Xiao-Shan Gao +2
Availability attacks, or unlearnable examples, are defensive techniques that allow data owners to modify their datasets in ways that prevent unauthorized machine learning models fr…
Disguised Copyright Infringement of Latent Diffusion Models
Yiwei Lu, Matthew Y. R. Yang, Zuoqiu Liu +2
Copyright infringement may occur when a generative model produces samples substantially similar to some copyrighted data that it had access to during the training phase. The notion…